{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:34UV2FHMBGYCPUJRXSXGSFVCHY","short_pith_number":"pith:34UV2FHM","schema_version":"1.0","canonical_sha256":"df295d14ec09b027d131bcae6916a23e2d9a07439eb0aaddfa17655d32d9b0d5","source":{"kind":"arxiv","id":"2512.17220","version":2},"attestation_state":"computed","paper":{"title":"Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiangnan Li, Jie Zhou, Junjie Wu, Mo Yu, Weiping Wang, Yuqing Li, Zheng Lin, Ziyan Zhou","submitted_at":"2025-12-19T04:08:29Z","abstract_excerpt":"Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior knowledge, interpret new information, and integrate evidence dispersed across a document, as revealed by the Mindscape-Aware Capability of humans in psychology. Current Retrieval-Augmented Generation (RAG) systems lack such guidance and therefore struggle with long-context tasks. In this paper, we propose Mindscape-Aware RAG (MiA-RAG), the first framework to formulate mindscape-aware retrieval and generation as a unified conditioning paradigm for LLM-b"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2512.17220","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-19T04:08:29Z","cross_cats_sorted":[],"title_canon_sha256":"1566ac09e82fe08cc844b2822bbf2a5f434635f92fb3c65268d3b1522a5c56a3","abstract_canon_sha256":"46244dcbace251756159a4931dc94fc7d5afcebc42aa66621e946ecb573da587"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:00.184663Z","signature_b64":"mE7CgZfnVRdOpoksbrNnlJgQPle4uzJYe0Ejm429Yvrx3uarpnghmahBtfxbXvyulkCJvBLMK77oISgsP++xCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df295d14ec09b027d131bcae6916a23e2d9a07439eb0aaddfa17655d32d9b0d5","last_reissued_at":"2026-05-29T01:05:00.183741Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:00.183741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiangnan Li, Jie Zhou, Junjie Wu, Mo Yu, Weiping Wang, Yuqing Li, Zheng Lin, Ziyan Zhou","submitted_at":"2025-12-19T04:08:29Z","abstract_excerpt":"Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior knowledge, interpret new information, and integrate evidence dispersed across a document, as revealed by the Mindscape-Aware Capability of humans in psychology. Current Retrieval-Augmented Generation (RAG) systems lack such guidance and therefore struggle with long-context tasks. In this paper, we propose Mindscape-Aware RAG (MiA-RAG), the first framework to formulate mindscape-aware retrieval and generation as a unified conditioning paradigm for LLM-b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.17220","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.17220/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2512.17220","created_at":"2026-05-29T01:05:00.183857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.17220v2","created_at":"2026-05-29T01:05:00.183857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.17220","created_at":"2026-05-29T01:05:00.183857+00:00"},{"alias_kind":"pith_short_12","alias_value":"34UV2FHMBGYC","created_at":"2026-05-29T01:05:00.183857+00:00"},{"alias_kind":"pith_short_16","alias_value":"34UV2FHMBGYCPUJR","created_at":"2026-05-29T01:05:00.183857+00:00"},{"alias_kind":"pith_short_8","alias_value":"34UV2FHM","created_at":"2026-05-29T01:05:00.183857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.06416","citing_title":"MiA-Signature: Approximating Global Activation for Long-Context Understanding","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01302","citing_title":"Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/34UV2FHMBGYCPUJRXSXGSFVCHY","json":"https://pith.science/pith/34UV2FHMBGYCPUJRXSXGSFVCHY.json","graph_json":"https://pith.science/api/pith-number/34UV2FHMBGYCPUJRXSXGSFVCHY/graph.json","events_json":"https://pith.science/api/pith-number/34UV2FHMBGYCPUJRXSXGSFVCHY/events.json","paper":"https://pith.science/paper/34UV2FHM"},"agent_actions":{"view_html":"https://pith.science/pith/34UV2FHMBGYCPUJRXSXGSFVCHY","download_json":"https://pith.science/pith/34UV2FHMBGYCPUJRXSXGSFVCHY.json","view_paper":"https://pith.science/paper/34UV2FHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.17220&json=true","fetch_graph":"https://pith.science/api/pith-number/34UV2FHMBGYCPUJRXSXGSFVCHY/graph.json","fetch_events":"https://pith.science/api/pith-number/34UV2FHMBGYCPUJRXSXGSFVCHY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34UV2FHMBGYCPUJRXSXGSFVCHY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34UV2FHMBGYCPUJRXSXGSFVCHY/action/storage_attestation","attest_author":"https://pith.science/pith/34UV2FHMBGYCPUJRXSXGSFVCHY/action/author_attestation","sign_citation":"https://pith.science/pith/34UV2FHMBGYCPUJRXSXGSFVCHY/action/citation_signature","submit_replication":"https://pith.science/pith/34UV2FHMBGYCPUJRXSXGSFVCHY/action/replication_record"}},"created_at":"2026-05-29T01:05:00.183857+00:00","updated_at":"2026-05-29T01:05:00.183857+00:00"}